Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mrauter1/botpipe --skill botpipe-workflow-authoringgit clone --depth 1 https://github.com/mrauter1/botpipeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mrauter1/botpipe/botpipe-workflow-authoring)<a href="https://agentmods.dev/skills/mrauter1/botpipe/botpipe-workflow-authoring"><img src="https://agentmods.dev/badge/skills/mrauter1/botpipe/botpipe-workflow-authoring.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01990 |
| Opus 5 | $0.00036 | $0.00995 |
| Sonnet 5 | $0.00014 | $0.00398 |
| Haiku 4.5 | $0.00007 | $0.00199 |
Grade A, and why
botpipe-workflow-authoring scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Botpipe Workflow Authoring
Start with repo truth
Inspect the local Botpipe sources before designing or editing a workflow. Prefer current repository behavior over this skill if they conflict.
Read the most relevant files first:
docs/authoring.mddocs/architecture.mddocs/workflow_authoring_guidelines.mdif present- Compact examples such as
botpipe/workflows/ralph_loop/ - Mature examples such as
botpipe/workflows/devloop/ - Meta-workflow examples under
labs/workflows/when building workflows that generate or optimize workflows
For nontrivial workflow design, also read references/botpipe-authoring-patterns.md from this skill.
Authoring defaults
Use the public authoring surface:
from botpipe import Workflow, Prompt, Route, FINISH
from botpipe import Json, Md, Text, Raw, step, produce_verify_step, workflow_step, python_step
Prefer these shapes:
- Workspace-local serious workflow:
.botpipe/workflows/<name>/flow.pyplus optionalspecs.py. - Packaged workflow:
botpipe/workflows/<name>/__init__.py,flow.pyorworkflow.py,workflow.toml, optionalprompts/,assets/, and tests. workflow.tomlis metadata only. Do not put topology, params, prompts, routes, or execution semantics there.
Expose workflow parameters through Params and read typed values from ctx.params. In bootstrap steps, project typed params into state and invocation artifacts instead of reparsing raw dictionaries.
Provider-heavy design
Assume the default provider is Codex CLI with gpt-5.5 unless local configuration says otherwise. Give Codex substantial agency for reasoning, code inspection, implementation choices, and repair loops.
Use deterministic python_step handlers only for narrow runtime duties:
- validate and snapshot parameters
- open workflow sessions
- write invocation contracts and publication receipts
- collect manifests or trace summaries
- normalize small structured inputs
- check required artifacts exist
Use produce_verify_step for broad work where Codex should reason over a codebase, traces, prompts, tests, or implementation tradeoffs. Producer prompts should specify the goal, evidence, deliverables, constraints, validation commands, and done criteria. They should not over-prescribe how to implement the task unless the repository contract requires it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 148 lines · 72 tokens per session scan A e84b63cd03ab
botpipe-workflow-authoring is a skill published in the GitHub repository mrauter1/botpipe (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,990 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agents-meet-rl
Troubleshooter for agentic-RL training, evaluation, and experiment design on LLM agents (single or multi-agent, multi-turn, tool-augmented). Routes a user's symptom to fixes anchored in the corpus. TRIGGER when: user is training, evaluating, or designing experiments for an RL-trained LLM agent; symptoms like reward…
goal-oriented
MUST use for ANY user request. This is a rigid requirement that applies to all tasks and conversations.
planning
MUST use after prompt-enhancer. Create implementation plan with MECE decomposition, dependency analysis, risk assessment, and mandatory plan-review.
mvp-first
Use when user requests complex systems involving multiple modules or subsystems - like 'build a XX system', 'design XX architecture', or 'implement XX with multiple features'. Triggers to prevent over-engineering before validating core assumptions.
ddd-tactical-design
Use when implementing domain logic, designing aggregates, entities, value objects, repositories, domain services, domain model design, ensuring data consistency, or when user mentions 'aggregate design', 'aggregate root', 'entity vs value object', 'domain event', 'repository pattern', 'domain service', 'data…
prompt-enhancer
MUST use before task execution. Clarify vague requirements, explore solutions, and ensure full understanding.